Janus-Shiau / lookahead_tensorflowLinks
Lookahead optimizer ("Lookahead Optimizer: k steps forward, 1 step back") for tensorflow
☆25Updated 6 years ago
Alternatives and similar repositories for lookahead_tensorflow
Users that are interested in lookahead_tensorflow are comparing it to the libraries listed below
Sorting:
- wrapping a keras optimizer to implement gradient accumulation☆119Updated 5 years ago
- lookahead optimizer for keras☆171Updated 5 years ago
- Focal Loss of multi-classification in tensorflow☆81Updated 6 years ago
- ☆31Updated 5 years ago
- Cyclic learning rate TensorFlow implementation.☆66Updated 6 years ago
- Converting A PyTorch Model to Tensorflow pb using ONNX☆162Updated 2 weeks ago
- Tensorflow version implementation of focal loss for binary and multi classification☆109Updated 6 years ago
- Try to use tf.estimator and tf.data together to train a cnn model.☆78Updated 7 years ago
- Radam+lookahead implemented by tensorflow☆11Updated 5 years ago
- ☆169Updated 4 years ago
- Keras implement of Lazy optimizer☆21Updated 5 years ago
- RAdam optimizer for keras☆71Updated 5 years ago
- Octave convolution☆34Updated 3 years ago
- bert-of-theseus via bert4keras☆31Updated 5 years ago
- The implementation of focal loss proposed on "Focal Loss for Dense Object Detection" by KM He and support for multi-label dataset.☆313Updated 7 years ago
- The unofficial tensorflow implementation of loss weights of in "Gradient Harmonized Single-stage Detector" published on AAAI 2019 (Oral).…☆29Updated 5 years ago
- Custom Optimizer in TensorFlow(定义你自己的Tensorflow Optimizer)☆66Updated 6 years ago
- Simple Tensorflow implementation of "On The Variance Of The Adaptive Learning Rate And Beyond"☆97Updated 5 years ago
- pytorch implement of Lookahead Optimizer☆194Updated 3 years ago
- Code for AAAI 2020 paper, Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks (Disout).☆217Updated 4 years ago
- Simple Tensorflow implementation of "Adaptive Gradient Methods with Dynamic Bound of Learning Rate" (ICLR 2019)☆150Updated 6 years ago
- LAMB Optimizer for Large Batch Training (TensorFlow version)☆121Updated 5 years ago
- Tensorflow2 implementation of CircleLoss. Support class-level, sparse class-level, pair-wise labels☆109Updated 5 years ago
- Train CNN model by tf.estimator☆29Updated 6 years ago
- tf2.0 implementation of circle loss☆32Updated 5 years ago
- A universal and efficient framework for training well-performing light net☆125Updated 8 years ago
- Knowledge distillation methods implemented with Tensorflow (now there are 11 (+1) methods, and will be added more.)☆265Updated 5 years ago
- saving memory by recomputing for keras☆37Updated 5 years ago
- 深度学习面试汇总,基本知识点的查漏补缺☆115Updated 7 years ago
- Corrupted labels and label smoothing☆129Updated 8 years ago